Dr Fiona Fidler

Honourary Associate

I have two main research interests – statistical cognition and eliciting expert judgement.

Statistical Cognition

Our projects in statistical cognition involve identifying typical misconceptions about statistical concepts and developing graphical displays and language for improved statistical communication.  These projects are strongly connected to the statistical reform of ecology, psychology and other disciplines (by statistical reform we mean the move away from over-reliance on statistical significance testing, dichotomous decisions made on the basis of p values to effect size estimation, confidence intervals, Bayesian techniques and other methods). 

My PhD thesis was about resistance to statistical reform in psychology, medicine and ecology. A pdf is available here:

Fidler, F. (2005). From Statistical Significance to Effect Estimation: Statistical Reform in Psychology, Medicine and Ecology. Department of History and Philosophy of Science, University of Melbourne.

On statistical cognition projects I have worked primarily with these people:
Prof. Mark Burgman, School of Botany, University of Melbourne
Prof. Geoff Cumming, School of Psychological Science, La Trobe University
Dr. Neil Thomason, Department of Philosophy, University of Melbourne
Dr. Sue Finch, Department of Mathematics and Statistics, University of Melbourne

Expert Judgement

Overconfidence in interval judgments is a common phenomenon.  In experts the phenomenon is even more pronounced: their estimates are systematically too narrow.  For example, when asked to guess a 90% interval for some value, experts usually provide bounds that correspond with 50% intervals.  In other words, they severely underestimate their own uncertainty.  My research looks for ways of eliciting interval judgments that have less systematic narrowing, and so provide estimates that more accurately characterise uncertainty.  This research forms part of a broader project called 'eliciting expert opinion'. The expert elicitation project is an Australian Centre for Excellence in Risk Analysis (ACERA) project, beginning January 2007. Others working on this broader project include: Mark Burgman, Terry Walshe, Marrisa McBride and Bonnie Wintle. 

Publications

Grants

Teaching

Links

Publications

Journal Articles

Fidler, F. and Loftus, G. (in review, invited). Why hypothesis testing is misunderstood: Hypostheses and data. Zeitschrift fuer Psychologie/Journal of Psychology.

Cumming, G and Fidler, F. (in review, invited). Confidence Intervals: Better Answers to Better Questions. Zeitschrift fuer Psychologie/Journal of Psychology.

Kalinowski, P., Fidler, F. and Cumming, G (in Press). Overcoming the inverse probability fallacy: A comparison of two teaching interventions. Methodology.

Beyth-Marom, R., Fidler, F. and Cumming G. (in press). Statistical Cognition: Towards Evidence-Based Practice in Statistics and Statistics Education. Statistics Education Research Journal.

Faulkner, C., Fidler, F. and Cumming, G. (2008). The Value of RCT Evidence Depends on the Quality of Statistical Analysis. Behaviour Research and Therapy, 46, 270-281

Walshe, T., Wintle, B., Fidler, F. & Burgman, M. (2007). Use of confidence intervals to demonstrate performance against forest management standards. Forest Ecology and Management, 247, 237-245

Wintle, B., Burgman, M. & Fidler, F. (2007). How fast should nanotechnology advance? Nature Nanotechnology, 2, 327.

Cumming, G., Fidler, F. and Vaux, D. (2007). Error bars in experimental biology.  Journal of Cell Biology, 177,  7-11. [Feature article] [Reprinted in Journal of Experimental Medicine, April 2007, 204, i11]

Fidler, F. & Cumming, G. (2007). Lessons learned from statistical reform efforts in other disciplines. Special Issue: Statistical reform in school psychology (Thomas J. Kehle and Melissa A. Bray, Eds.) Psychology in the Schools, 44, 441-449.

Cumming, G., Fidler, F., Leonard, M., Kalinowski, P., Christiansen, A., Kleinig, A., Lo, J., McMenamin, N. and Wilson, S. (2007).  Statistical reform in psychology: Is anything changing? Psychological Science, 18, 230-232.

Fidler, F., Burgman, M., Cumming, G. Buttrose, R. and Thomason., N. (2006). Impact of criticism of null hypothesis significance testing on statistical reporting practices in conservation biology. Conservation Biology, 20, 1539-1544.

Belia, S., Fidler, F., Williams, J. and Cumming, G. (2005). Researchers misunderstand confidence intervals and standard error bars. Psychological Methods, 10, 389-396.

Fidler, F., Thomason, N., Cumming, G., Finch, S. and Leeman, J. (2005). Still much to learn about confidence intervals. Reply to Rouder and Morey. Psychological Science, 16, 494-495.

Fidler, F., Cumming, G., Thomason, N., Pannuzzo, D., Smith, J., Fyffe, P., Edmonds, H., Harrington, C. and Schmitt, R. (2005). Toward improved statistical reporting in the Journal of Consulting and Clinical Psychology. Journal of Consulting and Clinical Psychology, 73, 136-143.

Fidler, F., Cumming, G., Burgman, M. and Thomason, N. (2004). Statistical reform in medicine, psychology and ecology. Journal of Socio Economics, 33, 615-630.

Fidler, F., Thomason, N., Cumming, G., Finch, S. and Leeman, J. (2004). Editors can lead researchers to confidence intervals but they can't make them think: Statistical reform lessons from Medicine. Psychological Science, 15, 119-126.

Cumming, G., Williams, J., and Fidler, F. (2004). Replication, and researchers’ understanding of confidence intervals and standard error bars. Understanding Statistics, 3, 299-311.  

Fidler, F. (2002). The 5th edition of the APA Publication Manual:  Why its statistics recommendations are so controversial. Educational and Psychological Measurement, 62, 749-770.  

Fidler, F. and Thompson, B. (2001). Computing Correct Confidence Intervals for ANOVA fixed and random effect sizes. Educational and Psychological Measurement, 61, 575-604.   

Geoff Cumming's webpage has pdfs of many of our joint papers: http://www.latrobe.edu.au/psy/cumming/current_res.html

top of page

Book Chapters

Fidler, F. (in press, invited). Statistical Significance, Result Worthiness and Evidence: What lessons are there for giftedness education in other disciplines? In B. Thompson & R. Subotnik (Eds.). Research Methodologies for conducting research on giftedness.

Cumming, G. &  Fidler, F. (in press).  The New Stats: Effect sizes and confidence intervals.  In G.R. Hancock & R. O. Mueller (Eds).  Quantitative methods in the social and behavioural sciences: A guide for researchers and reviewers. Erlbaum.

Fidler, F. & Cumming, G. (2008). The new stats: Attitudes for the twenty-first century. (Ch 1). In J.W. Osborne (Ed.). Best Practice in Quantitative Methods (pp. 1-12) . Sage.

Fidler, F., Faulkner, S. & Cumming, G. (2008). Analyzing and presenting outcomes: Focus on effect size estimates and confidence intervals. In A.M. Nezu. & C.M. Nezu (Eds.) Evidence-Based outcome research: A Practical guide to conducting randomized controlled trials for psychosocial interventions (pp.315-334). New York: OUP.

DiStefano, J., Fidler, F. & Cumming, G. (2005). Effect size estimates and confidence intervals: An alternative focus for the presentation and interpretation of ecological data.  (Ch 3, pp. 71-102).  In A.R. Burk (Ed.) New Trends in Ecology Research. Hauppauge NY: Nova Science Publishers.

top of page

Refereed Conference Proceedings (published proceedings)

Fidler, F. (2006).  Should Psychology abandon p values and teach confidence intervals instead?  Evidence-based reforms in statistics education.  Working co-operatively in statistics education.  Proceedings of ICOTS-7, Seventh International Conference on Teaching Statistics. Salvador, Brazil.

Cumming, G. and Fidler, F. (2005).  Interval estimates for statistics communication: Problems and possible solutions. Proceedings of Statistics Education and the Communication of Statistics, International Association for Statistics Education. Sydney, Australia.

Cumming, G., Fidler, F. and Thomason, N. (2002). The statistical re-education of psychology. In B. Phillips (Ed.) Developing a statistically literate society. Proceedings of ICOTS-6, Sixth International Conference on Teaching Statistics, 1-6. Voorburg, The Netherlands.

Fidler, F. (2005).Confidence Intervals in practice. Proceedings of the 55th International Statistics Institute Session. Sydney, Australia.

Fidler, F. and Cumming, G. (2005). Teaching confidence intervals: Problems and potential solutions. Proceedings of the 55th International Statistics Institute Session. Sydney, Australia.

Refereed Conference Presentations (no published proceedings)

Fidler, F. (2005).  "Is a ban necessary?" Paper presented in All Academy Symposium: “Proposed: The Academy should ban null hypothesis testing from its journals” (Calahoun, M., Starbuck, W., Thompson, B., Fidler, F. and Abrahamson, E.) at the 65th Annual Meeting of the Academy of Management, Honolulu, Hawaii, USA (August).

Fidler, F. Faulkner, S. and Cumming, G. (2004).  How should results be reported? ‘The New Stats’, and an evidence-based approach to improving research communication in psychology.  Symposium presented to the 39th Annual Australian Psychological Society, Sydney (October).

Fidler, F., Burgman, M., Thomason, N., Cumming, G. and Buttrose, R. (2003)   The Informed Regulator Rule: How Confidence Intervals can help Wildlife Management.  Paper presented at International Wildlife Management Congress, Christchurch, New Zealand (December).

Fidler, F., Cumming, G., Burgman, M., Buttrose, R. and Thomason, N. (2003).  Teaching a precautionary approach to statistically non-significant results in Ecology: How Confidence Intervals can help.  Paper presented at OZCOTS (Australian Conference on Teaching Statistics), Melbourne (December).

Fidler, F. (2003). Why medicine had a statistical reform and psychology didn't.  Paper presented to Australasian Association of History, Philosophy and Social Studies of Science (AAHPSSS), Melbourne (July)

Fidler, F., Buttrose, R., Burgman, M., Thomason, N. and Cumming, G. (2002). Statistical reporting deficiencies in conservation biology. Paper presented to the Ecological Society of Australia, Cairns (December).  
    
Fidler, F. and Cumming, G. (2002). Confidence Intervals and the statistical re-education of psychology. Symposium presented at the 110th Annual American Psychological Association Convention, Chicago, IL, USA (August).

Fidler, F., Cumming, G., Thomason, N., Finch, S. and Leeman, J. (2001). What can medicine teach psychology about statistical reform? Paper presented at OZCOTS (Australian Conference on Teaching Statistics), Melbourne (December).

Fidler, F., Edmonds, H., Fyffe, P., Harrington, C., Pannuzzo, D., Schmitt, R., Smith, J. and Cumming, G. (2001). Editorial influence on statistical practices in the Journal of Consulting and Clinical Psychology. Paper presented at OZCOTS (Australian Conference on Teaching Statistics), Melbourne (December).

Williams, J., Fidler, F., and Cumming, G. (2001). Researchers’ interpretation of graphically-presented confidence intervals and other error bars: Implications for replication.  Paper presented at OZCOTS (Australian Conference on Teaching Statistics), Melbourne (December).

Belia, S., Fidler, F. and Cumming, G. (2001) Researchers’ interpretation of the width of graphically-presented confidence intervals and other error bars. Paper presented at OZCOTS (Australian Conference on Teaching Statistics), Melbourne (December).

Fidler, F.  (2001). Statistical Reform in Psychology and Medicine: A comparison of debates over statistical significance testing and changes in data reporting practices.  Paper presented to Australasian Association of History, Philosophy and Social Studies of Science (AAHPSSS), Melbourne (July).

Loh, Z. and Fidler, F.  (2001). Null Hypothesis Significance Testing: Can the damage be assessed?  Paper presented to the Australasian Association of History, Philosophy and Social Studies of Science (AAHPSSS), Melbourne (July).

Fidler, F. and Finch, S. (2000). Students’ understanding of Confidence Intervals: Descriptive or Inferential Statistic?  Paper presented at OZCOTS (Australian Conference on Teaching Statistics), Melbourne (December).

Fidler, F. (2000).  Reforming Psychology: Neglected issues.  Paper presented to the Australasian Association of History, Philosophy and Social Studies of Science (AAHPSSS), Sydney (July).

top of page

Poster Presentations

Lai, J., Fidler, F., & Cumming, G. (2008, submitted). Researchers under-estimate the variability of p values over replication. APA Convention, Boston, August.

Lai, J., Fidler, F., & Cumming, G. (2007). Interval Judgment where variability is real: The case of statistical replication. Poster presented to the Society for Judgment and Decision Making (JDM), Long Beach, CA, November.

Speirs-Bridge, A., Fidler, F., McBride, M., Cumming, G., Flander, L., and Burgman, M. (2007). Evaluating Experts Interval Judgments. Poster presented to the Society for Judgment and Decision Making (JDM), Long Beach, CA, November.

Wintle, B.C., Fidler, F., and Burgman, M. (2007). Scientific Objectivity: Everyone's imaginary friend. Poster presented to the Society for Judgment and Decision Making (JDM), Long Beach, CA, November.

Fidler, F. (2006). From statistical significance to effect estimation. Poster presented to the Summer Institute on Bounded Rationality, Max Plank Institute of Human Development, Berlin, August

Journal Articles in preparation

Faulkner, C., Fidler, F. & Cumming, G. Widespread statistical problems delay progress in clinical psychology.  Manuscript in preparation.

Cumming, G., Coulson, M., Healey, M. & Fidler, F. Confidence interval pictures can give better inference than significance testing.  Manuscript in preparation.

Grants

Cumming, G. and Fidler, F. 
Funding: 2007-2010, $355, 852. Evidence based improvement of statistical inference practices in psychology and other disciplines.  ARC Discovery Grant and Australian Post-doctoral Fellowship.  (School of Psychological Science, La Trobe University).

Teaching

I’ve taught in a few different departments, but predominantly in psychology.

Psychology

Undergraduate Lectures

I lectured for two years (2005 & 2006) in the School of Psychological Science at La Trobe University.
My primary teaching commitment there was Practical Research Methods (Qualitative and Quantitative) in third year psychology (PSY30PY).  I also contributed to teaching intro Psychological Studies (PSY11PSA & PSY11PSB).

I am currently an honourary associate of the School of Psychological Science at La Trobe and I continue to teach a methods stream in third year psychology and to supervise students.

Supervision

Current

I am supervising 2 honours students in psychology 2008:

Debbie Hansen: Meta-analysis and the progress of science.

Rachel Hamilton-Keene: Prevalence and impact of the CI overlap misconseption in medical literature.

I am co-supervising 2 PhD students in psychology:
Pawel Kalinowski
Jerry Lai

Previous

2007
Simon Carter: Students' misconceptions about confidence intervals.

Andrew Speirs-Bridge: Eliciting interval judgments of future disease rates from population health experts. Andrew's work was recently presented at the Society for Judgment and Decision Making. Next year he begins a Masters program in psychology.

2006
Pav Kalinowski: Overcoming the inverse probability fallacy. Pav conducted a teaching experitment, to see whether instruction in either Bayes theorem or formal logic can help overcome the 'inverse probability fallacy' and other misconceptions associated with frequentist p values. He has some very nice results that he is currently writing up for publication.

Environmental Science

I usually participate in the teaching of Environmental Risk Assessment (606-303).

History and Philosophy of Science

During my PhD in the Department of History and Philosophy of Science at the University of Melbourne, I tutored in several different subjects including:  Human Values, Social Change and New Technologies; History of Astronomy (136-101); Science, Philosophy and History (136-031); Science, Life and Mind  (136-334). 

top of page

Links

Geoff Cumming's webpage  has pdfs of many of our papers and other statistical reform related things, including Exploratory Software for Confidence Intervals, ESCI: http://www.latrobe.edu.au/psy/cumming/current_res.html